# HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers

arXiv: https://arxiv.org/abs/2606.01132 · HTML: https://mlsanity.com/paper/2606.01132/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 31 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 19 of 19)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [DVQA: Understanding Data Visualizations via Question Answering](https://mlsanity.com/paper/1801.08163/) (2018)
- [PlotQA: Reasoning over Scientific Plots](https://mlsanity.com/paper/1909.00997/) (2019)
- [FigureQA: An Annotated Figure Dataset for Visual Reasoning](https://mlsanity.com/paper/1710.07300/) (2017)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Chart-to-Text: A Large-Scale Benchmark for Chart Summarization](https://mlsanity.com/paper/2203.06486/) (2022)
- [ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering](https://mlsanity.com/paper/2504.05506/) (2025)
- [A Rosetta Stone for AI Benchmarks](https://mlsanity.com/paper/2512.00193/) (2025)
- [MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space](https://mlsanity.com/paper/2506.11684/) (2025)
- [Evaluating Multimodal Large Language Models on Vertically Written Japanese Text](https://mlsanity.com/paper/2511.15059/) (2025)
- [POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering](https://mlsanity.com/paper/2507.11939/) (2025)
- [JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation](https://mlsanity.com/paper/2604.00909/) (2026)

## Abstract (arXiv)

Understanding chart and table images is essential for applying vision-language models (VLMs) to real-world document understanding. While English benchmarks have advanced rapidly, non-English counterparts remain scarce, leaving it unclear whether this progress generalizes across languages. A key obstacle is the difficulty of collecting realistic and diverse non-English chart and table images at scale. To address this, we leverage governmental white papers as a source for benchmark construction, as they contain naturally occurring charts and tables across diverse formats and domains and are freely accessible in many countries. As a first instantiation, we introduce HakushoBench, a Japanese chart and table VQA benchmark built from 33 governmental white papers. HakushoBench contains 2,053 images spanning over 10 image types, with manually annotated and independently verified QA pairs designed to assess holistic understanding of charts and tables rather than local visual cues alone. Experiments across a broad range of VLMs show that HakushoBench is substantially harder than the existing Japanese benchmark and remains challenging for open-weight models: sub-10B open-weight models reach at most 58.6% accuracy, and even the flagship open-weight model Qwen3.5-397B-A17B trails Gemini~3~Pro by 8.1 points (85.8% vs. 93.9%), highlighting substantial room for improvement in complex chart and table understanding. We release our dataset and code.